Related papers: DETReg: Unsupervised Pretraining with Region Prior…

Recently, DEtection TRansformer (DETR), an end-to-end object detection pipeline, has achieved promising performance. However, it requires large-scale labeled data and suffers from domain shift, especially when no labeled data is available…

While supervised object detection methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on. To address this in scenarios where annotating data is…

This paper presents a general scheme for enhancing the convergence and performance of DETR (DEtection TRansformer). We investigate the slow convergence problem in transformers from a new perspective, suggesting that it arises from the…

In this paper, we address the limitations of the DETR-based semi-supervised object detection (SSOD) framework, particularly focusing on the challenges posed by the quality of object queries. In DETR-based SSOD, the one-to-one assignment…

Existing object detection models are mainly trained on large-scale labeled datasets. However, annotating data for novel aerial object classes is expensive since it is time-consuming and may require expert knowledge. Thus, it is desirable to…

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using…

Pre-training is a dominant paradigm in computer vision. For example, supervised ImageNet pre-training is commonly used to initialize the backbones of object detection and segmentation models. He et al., however, show a surprising result…

Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…

The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…

In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Faster-RCNN or DETR) which enable outstanding performance on…

Open world object detection aims at detecting objects that are absent in the object classes of the training data as unknown objects without explicit supervision. Furthermore, the exact classes of the unknown objects must be identified…

The use of pretrained deep neural networks represents an attractive way to achieve strong results with few data available. When specialized in dense problems such as object detection, learning local rather than global information in images…

The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a…

In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing the traditional paradigm of pre-training followed by full fine-tuning. PET is particularly favored for its effectiveness in large foundation…

This paper presents LP-DETR (Layer-wise Progressive DETR), a novel approach that enhances DETR-based object detection through multi-scale relation modeling. Our method introduces learnable spatial relationships between object queries…

The performance of a trained object detection neural network depends a lot on the image quality. Generally, images are pre-processed before feeding them into the neural network and domain knowledge about the image dataset is used to choose…

Training image-based object detectors presents formidable challenges, as it entails not only the complexities of object detection but also the added intricacies of precisely localizing objects within potentially diverse and noisy…

Pretraining on large labeled datasets is a prerequisite to achieve good performance in many computer vision tasks like 2D object recognition, video classification etc. However, pretraining is not widely used for 3D recognition tasks where…

In this work we present point-level region contrast, a self-supervised pre-training approach for the task of object detection. This approach is motivated by the two key factors in detection: localization and recognition. While accurate…

This paper presents a DETR-based method for cross-domain weakly supervised object detection (CDWSOD), aiming at adapting the detector from source to target domain through weak supervision. We think DETR has strong potential for CDWSOD due…